Triple
T25773062
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Johannesburg Expo Centre |
E649072
|
entity |
| Predicate | oneOfLargestIn |
P30645
|
FINISHED |
| Object | South Africa |
—
|
NE NERFINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: South Africa | Statement: [Johannesburg Expo Centre, oneOfLargestIn, South Africa]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: oneOfLargestIn Context triple: [Johannesburg Expo Centre, oneOfLargestIn, South Africa]
-
A.
oneOfLargest
chosen
Indicates that the subject is among the largest members within a specified group or set, but not necessarily the single largest.
-
B.
madeStateOneOfLargestIn
Indicates that an entity caused a state to become one of the largest within a specified group, category, or region.
-
C.
largestInCountry
Indicates that an entity is the largest of its kind within the specified country.
-
D.
oneOfHighest
Indicates that the subject is among the top-ranked or best-performing entities within a specified group or category.
-
E.
isLargestCityIn
Indicates that one city has the greatest population or size compared to all other cities within a specified region or administrative area.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69e7ab333b508190b6d708d8d9a328ed |
completed | April 21, 2026, 4:52 p.m. |
| NER | Named-entity recognition | batch_69f60c3b09488190ade1b69ff7f0df0e |
completed | May 2, 2026, 2:37 p.m. |
| PD | Predicate disambiguation | batch_69f60b8461ac81908c5bd3d73eed59f4 |
completed | May 2, 2026, 2:34 p.m. |
Created at: April 22, 2026, 5:31 a.m.